Minimum-seeking properties of analog neural networks with multilinear objective functions
From MaRDI portal
Publication:4850480
DOI10.1109/9.402228zbMath0833.65056MaRDI QIDQ4850480
Publication date: 25 February 1996
Published in: IEEE Transactions on Automatic Control (Search for Journal in Brave)
Full work available at URL: https://semanticscholar.org/paper/3998ccf080a83db2e5f365e72a1a07051a5f3dc1
neural network; dynamical system; nonlinear programming; interior-point methods; discrete optimization; multilinear objective functions
65K10: Numerical optimization and variational techniques
90C05: Linear programming
92B20: Neural networks for/in biological studies, artificial life and related topics
49J15: Existence theories for optimal control problems involving ordinary differential equations
Related Items
Comparison of convergence and stability properties for the state and output solutions of neural networks, Dynamical Analysis of Continuous Higher-Order Hopfield Networks for Combinatorial Optimization, Are analog neural networks better than binary neural networks?, Linear systems in a saturated mode and convergence as gain becomes large of asymptotically stable equilibrium points of neural nets, Continuous dynamical systems that realize discrete optimization on the hypercube